8 citations · 14 across the 13 of their papers we have counts for
14 papers
Tail-Likelihood Reinforcement Learning
Shrinivas Ramasubramanian, Daman Arora, Fahim Tajwar +11
Reinforcement learning typically optimizes average reward. For generative policies, the average can hide an important distinction: two policies can achieve the same mean reward whi…
Retrospective In-Context Learning for Temporal Credit Assignment with Large Language Models
Wen-Tse Chen, Jiayu Chen, Fahim Tajwar +4
Learning from self-sampled data and sparse environmental feedback remains a fundamental challenge in training self-evolving agents. Temporal credit assignment mitigates this issue…
Expanding the Capabilities of Reinforcement Learning via Text Feedback
Yuda Song, Lili Chen, Fahim Tajwar +5
The success of RL for LLM post-training stems from an unreasonably uninformative source: a single bit of information per rollout as binary reward or preference label. At the other…
Maximum Likelihood Reinforcement Learning
Fahim Tajwar, Guanning Zeng, Yueer Zhou +7
Reinforcement learning (RL) is the method of choice for training models in setups where the objective function can only be evaluated by sampling from the model. Our key observation…
Reasoning as an Adaptive Defense for Safety
Taeyoun Kim, Fahim Tajwar, Aditi Raghunathan +1
Reasoning methods that adaptively allocate test-time compute have advanced LLM performance on easy to verify domains such as math and code. In this work, we study how to utilize th…
Accelerating Diffusion Planners in Offline RL via Reward-Aware Consistency Trajectory Distillation
Xintong Duan, Yutong He, Fahim Tajwar +3
Although diffusion models have achieved strong results in decision-making tasks, their slow inference speed remains a key limitation. While consistency models offer a potential sol…